IPAC2021 - List of Authors (Chandler, E.)

Paper	Title	Page
WEPAB323	High Performance DAQ Infrastructure to Enable Machine Learning for the Advanced Photon Source Upgrade	3434
	G. Shen, N.D. Arnold, T.G. Berenc, J. Carwardine, E. Chandler, T. Fors, T.J. Madden, D.R. Paskvan, C. Roehrig, S.E. Shoaf, S. Veseli ANL, Lemont, Illinois, USA
	Funding: Argonne National Laboratory’s work was supported by the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, under contract DE-AC02-06CH11357. It is well known that the efficiency of an advanced control algorithm like machine learning is as good as its data quality. Much recent progress in technology enables the massive data acquisition from a control system of modern particle accelerator, and the wide use of embedded controllers, like field-programmable gate arrays (FPGA), provides an opportunity to collect fast data from technical subsystems for monitoring, statistics, diagnostics or fault recording. To improve the data quality, at the APS Upgrade project, a general-purpose data acquisition (DAQ) system is under active development. The APS-U DAQ system collects high-quality fast data from underneath embedded controllers, especially the FPGAs, with the manner of time-correlation and synchronously sampling, which could be used for commissioning, performance monitoring, troubleshooting, and early fault detection, etc. This paper presents the design and latest progress of APS-U high-performance DAQ infrastructure, as well as its preparation to enable the use of machine learning technology for APS-U, and its use cases at APS.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-WEPAB323
About •	paper received ※ 19 May 2021 paper accepted ※ 24 June 2021 issue date ※ 29 August 2021
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Page

High Performance DAQ Infrastructure to Enable Machine Learning for the Advanced Photon Source Upgrade

3434

G. Shen, N.D. Arnold, T.G. Berenc, J. Carwardine, E. Chandler, T. Fors, T.J. Madden, D.R. Paskvan, C. Roehrig, S.E. Shoaf, S. Veseli
ANL, Lemont, Illinois, USA

Funding: Argonne National Laboratory’s work was supported by the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, under contract DE-AC02-06CH11357.
It is well known that the efficiency of an advanced control algorithm like machine learning is as good as its data quality. Much recent progress in technology enables the massive data acquisition from a control system of modern particle accelerator, and the wide use of embedded controllers, like field-programmable gate arrays (FPGA), provides an opportunity to collect fast data from technical subsystems for monitoring, statistics, diagnostics or fault recording. To improve the data quality, at the APS Upgrade project, a general-purpose data acquisition (DAQ) system is under active development. The APS-U DAQ system collects high-quality fast data from underneath embedded controllers, especially the FPGAs, with the manner of time-correlation and synchronously sampling, which could be used for commissioning, performance monitoring, troubleshooting, and early fault detection, etc. This paper presents the design and latest progress of APS-U high-performance DAQ infrastructure, as well as its preparation to enable the use of machine learning technology for APS-U, and its use cases at APS.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-WEPAB323

About •

paper received ※ 19 May 2021 paper accepted ※ 24 June 2021 issue date ※ 29 August 2021

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)